mdr_request_review

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses critical behavioral traits beyond annotations: the tool blocks the agent from reading/editing files under review while waiting, because the user is actively writing @comment markers. It explains the consequence of ignoring this (surfacing unsubmitted markers) and clarifies that after a 'batch' or 'done' result, the agent may only address comments listed in that result. This is rich, actionable behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence earns its place given the tool's complexity. It front-loads the core purpose and usage, then covers the critical waiting behavior and post-batch constraints. The structure is logical: purpose → when to use → new vs continue → critical warning → post-result rules. Slightly verbose but justified by the need to prevent misuse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 params, no output schema, no annotations), the description is remarkably complete. It covers when to use, how to start/continue, the critical waiting constraint, what happens after results arrive, and the relationship with mdr_baseline. The only minor gap is the exact meaning of enableResolve, but the schema covers that and the description mentions the resolve workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all three parameters. The description adds meaningful context beyond the schema: it explains the relationship between filePaths and sessionId (mutually exclusive usage), and clarifies that sessionId is used to continue after addressing a batch. It also explains the purpose of enableResolve implicitly through the resolve workflow mention, though it doesn't detail the workflow.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: open markdown files in mdr for the user to review and comment on, or continue an existing review session. It uses specific verbs ('open', 'review', 'comment') and explicitly distinguishes the user as the reviewer while the agent waits and addresses comments. It also differentiates from siblings by naming mdr_baseline and explaining when to use it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use guidance, including example phrasings like 'I want to review X in mdr' and 'open X so I can comment'. It clearly states when to pass filePaths (new review) vs sessionId (continue/re-poll), and when to call mdr_baseline before editing. It also gives a critical exclusion: do not use other tools on files under review while waiting.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.